Sensor Data Interpolation via Context-Aware Network
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Missing values in sensor data can lead to information omission and operational restrictions, especially when using low-priced sensors with low stability, as they have a higher probability of data loss, affecting the reliability of sensor systems.
Innovation Solution
A method and device that utilize an interpolation network, trained on complete sensor signals, to generate interpolated signals by identifying and filling missing parts based on context recognition, minimizing data loss and enhancing sensor data reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If low-priced sensors are used to increase sensor installation density and reduce cost, then the number of sensors that can be installed increases and spatial resolution improves, but the probability of missing value occurrence increases due to low stability
Solution Approach 1:
The patent creates a virtual copy of the missing sensor data through interpolation. The interpolation network generates interpolated signals that replicate what the missing sensor readings would have been, based on patterns learned from complete signals. This allows the system to use low-priced sensors while maintaining data reliability through generated copies of missing information.
Solution Approach 2:
The patent transforms the sensor data from incomplete to complete by changing the parameter completeness. The interpolation network learns the underlying patterns and parameters of sensor signals, then uses these to generate missing data points, effectively changing the completeness parameter of the sensor data without changing the physical sensors themselves.
2Quantity of substance
If low-priced sensors are used to increase sensor installation density, then spatial resolution improves, but information omission increases due to data loss
Solution Approach 1:
The interpolation network creates copies of missing data points by learning from complete signal patterns. When data is lost from low-priced sensors, the system generates interpolated copies that restore the missing information, maintaining spatial resolution while preventing information loss.
Solution Approach 2:
The interpolation network acts as an intermediary between the incomplete sensor data and the required complete data. It mediates the data loss problem by processing incomplete signals and generating the missing intermediate values, allowing high-density sensor installation without information omission.
3Device complexity
If missing values are not interpolated, then the system operates simply without additional processing, but information omission occurs and operational reliability decreases
Solution Approach 1:
The system performs preliminary action by training the interpolation network in advance using complete sensor signals. This pre-trained model is then ready to quickly interpolate missing values during operation, maintaining operational reliability without adding complex real-time processing while preserving system simplicity.
Data Source
AI summary
A method for interpolating a missing value of the present invention comprises the steps of: collecting, by a data processing unit, a data set obtained by selecting an intact whole signal without a missing part from among a plurality of unit signals configuring a sensor signal; training, by a training unit, an interpolation network for interpolating a missing part in a missing signal having the missing part, wherein at least a part of a sensor signal is missing, by using the data set; receiving, by an interpolation unit, an input of the missing signal in which at least a part of the sensor signal is missing; and generating, by the interpolation unit, an interpolation signal by interpolating the missing part by using the interpolation network.